Kuaidi100 launched China's first MCP-protocol-compatible logistics information service platform. The core API services of Kuaidi100's Baidiy
Nothing to run from here
CXT Software MCP by usefulapi is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
14
tools declared
remote
at its publisher
—
calls last 7d
What it does
Track and search CXT courier orders, check drivers, propose and save order and route plans.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http cxt-software-mcp-by-usefulapi https://cxt-software.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# cxt_track_shipments, cxt_search_shipments, cxt_list_recent_orders and 11 more
CXT Software MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 578 servers
usefulapi578 servers
25 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http cxt-software-mcp-by-usefulapi https://cxt-software.usefulapi.io/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
14 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Track orders and route stops by tracking number: matches a parcel reference, a parcel item barcode, or Reference1/Reference2 of an order or route stop. Returns shipment summaries with status events and proof of delivery as far as the caller's permissions allow: an INET login sees the most detail; with an Operations App login this endpoint is called without credentials (CXT lists only internet user
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tracking_numbers | array | yes | Tracking numbers, references or barcodes (1-50). |
| include_partial_match | boolean | no | Also return partial matches (default false). |
| begin_date | string | no | A date (2026-10-01) or an ISO 8601 date-time with a timezone, e.g. 2026-10-01T08:00:00Z. |
| end_date | string | no | A date (2026-10-01) or an ISO 8601 date-time with a timezone, e.g. 2026-10-01T08:00:00Z. |
| page_num | integer | no | CXT's pageNum, documented as 'the offset for the records to return' (default 0). When has_more is true, ask for the next records and check the new page does not repeat the previous one (if it does, pa |
| page_size | integer | no | Results per page, 1-1000 (default 50). |
Search orders and route stops by place, address, city, state, postal code, order template, or only by date range. tracking_type says which field search_criteria is matched against: Location (origin/destination or stop name), Address, City, State, Postal (zip or zip+4), Template (order template name), Tracking (references/barcodes) or DateOnly (no criteria: everything between begin_date and end_dat
| Parameter | Type | Required | Notes |
|---|---|---|---|
| tracking_type | string | yes | Which field search_criteria matches. |
| search_criteria | array | no | Values to match (omit for DateOnly). |
| include_partial_match | boolean | no | Also return partial matches (default false). |
| begin_date | string | no | A date (2026-10-01) or an ISO 8601 date-time with a timezone, e.g. 2026-10-01T08:00:00Z. |
| end_date | string | no | A date (2026-10-01) or an ISO 8601 date-time with a timezone, e.g. 2026-10-01T08:00:00Z. |
| page_num | integer | no | CXT's pageNum, documented as 'the offset for the records to return' (default 0). When has_more is true, ask for the next records and check the new page does not repeat the previous one (if it does, pa |
| page_size | integer | no | Results per page, 1-1000 (default 50). |
The most recent orders of the signed-in INTERNET user (user type INET; the orders of their account). Costs 1 API credit with the vendor. POST /v2/Shipments/Summaries with numRecentOrders.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| count | integer | no | How many recent orders, 1-1000 (default 25). |
One on-demand order with its status, confirmation, pickup, delivery and proof-of-delivery details, as an INTERNET user sees it (sign in with user type INET). Optionally with the itemized charges. Operations App users should use cxt_get_dispatch_order. Costs 1 API credit with the vendor. GET /v2/Orders/{orderId}/{includeItemizedCharges}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | number | yes | CXT order id. |
| include_itemized_charges | boolean | no | Include the itemized charges (default false). |
One on-demand order with itemized charges, as an OPERATIONS APP (X Dispatch) user sees it (sign in with user type XDISPATCH): addresses, times, driver, status events, proof of delivery. Costs 1 API credit with the vendor. GET /v2/Dispatch/Orders/{onDemandOrderId}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_id | number | yes | CXT on-demand order id. |
The itinerary planning limits of this X Dispatch system: maxAllowedStops (shipments x 2), maxAllowedLocations and maxAllowedPlaceholders. Needs an Operations App user with the ITINERARY_PLANNING_ACCESS permission. GET /v3/ItineraryPlanning/Settings.
No parameter schema on file.
Check whether drivers are available to be planned: for each driver id, vehicle violations (for example an expired inspection) and HR violations (for example not scheduled), each with isBypassable. Changes nothing. Needs ITINERARY_PLANNING_ACCESS. POST /v3/ItineraryPlanning/Orders/Drivers/Validate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| driver_ids | array | yes | Driver ids to check. |
Check one driver against specific orders: vehicle violations, HR violations and capability violations (for example Hazmat or Lift Gate that the driver lacks). Changes nothing. Needs ITINERARY_PLANNING_ACCESS. POST /v3/ItineraryPlanning/Orders/Drivers/{driverId}/Validate.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| driver_id | integer | yes | Driver id. |
| order_ids | array | yes | Order ids to check the driver against. |
Generate a proposed itinerary that assigns on-demand orders to drivers (pickup and delivery stops in sequence, with times, distance and unassigned stops). This only PROPOSES a plan: nothing is dispatched until cxt_save_order_plan is called. Needs ITINERARY_PLANNING_ACCESS. Check the limits with cxt_get_planning_limits first. POST /v3/ItineraryPlanning/Orders.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| order_ids | array | yes | Order ids to plan. |
| driver_ids | array | yes | Driver ids to plan onto. |
| start_time | string | yes | Planning window start, local time, e.g. 2026-10-01T08:00:00. |
| end_time | string | yes | Planning window end, local time, e.g. 2026-10-01T18:00:00. |
| num_placeholders | integer | no | Virtual placeholder drivers (0-1000). |
| max_orders_per_driver | integer | no | — |
| goal | string | no | Optimization goal (default QUICKEST_ROUTE). |
| enhanced_routing | string | no | Enhanced routing (default OFF). |
Re-optimize a single driver's plan after manual changes (proposal only: nothing is dispatched until cxt_save_order_plan). Needs ITINERARY_PLANNING_ACCESS. POST /v3/ItineraryPlanning/Orders/Optimize.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| driver_id | integer | yes | Driver id (or the placeholder's id when is_placeholder). |
| is_placeholder | boolean | no | The driver is a placeholder. |
| plan_order_ids | array | yes | Orders currently in this driver's plan. |
| all_input_order_ids | array | yes | All orders in the planning run. |
| start_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| end_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| goal | string | no | Optimization goal (default QUICKEST_ROUTE). |
| enhanced_routing | string | no | Enhanced routing (default OFF). |
Generate a proposed re-sequencing of the stops of existing routes for one route date (stops move between the output routes, with times, distance and unassigned stops). Proposal only: nothing changes until cxt_save_route_plan is called. Needs ITINERARY_PLANNING_ACCESS. POST /v3/ItineraryPlanning/Routes/{postDate}.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_date | string | yes | Route date, yyyy-mm-dd. |
| input_route_ids | array | yes | Route ids to take stops from. |
| output_route_ids | array | yes | Route ids to assign stops to. |
| start_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| end_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| num_placeholders | integer | no | — |
| max_stops_per_route | integer | no | — |
| excluded_stop_ids | array | no | Stop ids to leave out of planning. |
| service_time_per_stop | integer | no | Service time per stop, minutes. |
| grace_period_per_stop | integer | no | Grace period per stop, minutes. |
| goal | string | no | Optimization goal (default QUICKEST_ROUTE). |
| enhanced_routing | string | no | Enhanced routing (default OFF). |
Re-optimize a single route after manual changes (proposal only: nothing changes until cxt_save_route_plan). Needs ITINERARY_PLANNING_ACCESS. POST /v3/ItineraryPlanning/Routes/{postDate}/Optimize.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_date | string | yes | Route date, yyyy-mm-dd. |
| route_id | string | yes | Route to optimize. |
| is_placeholder | boolean | no | — |
| plan_stop_ids | array | no | Stops currently assigned to this route. |
| input_route_ids | array | no | Source routes for stops. |
| excluded_stop_ids | array | no | — |
| start_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| end_time | string | yes | Local date-time without timezone, e.g. 2026-10-01T08:00:00. |
| is_batch_call | boolean | no | Batch optimization (default false). |
| goal | string | no | Optimization goal (default QUICKEST_ROUTE). |
| enhanced_routing | string | no | Enhanced routing (default OFF). |
COMMIT an order plan: assigns the orders to the drivers and DISPATCHES them (drivers receive the work in the driver app; customers may be notified by the system's own status rules). Use only after the user has seen and approved the plan from cxt_plan_orders / cxt_optimize_order_plan. Pass each driver's stops from the plan reply: id, type (PICKUP or DELIVERY), sequence and from (the scheduled time)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| plans | array | yes | — |
| driver_pay_locked_status | string | no | What to do with already locked driver pay: KEEP_LOCKED_AND_DISPATCH or UNLOCK_AND_DISPATCH. |
| confirm | boolean | yes | Must be true: the user approved this plan and wants it dispatched to the drivers now. |
COMMIT a route plan for one route date: moves and re-sequences route stops as in the plan and DISPATCHES the changed routes to drivers. Use only after the user has seen and approved the plan from cxt_plan_routes / cxt_optimize_route_plan. Pass each route's stops from the plan reply: id, sequence and from (the scheduled time). Response is empty on success (204). Needs ITINERARY_PLANNING_ACCESS. POS
| Parameter | Type | Required | Notes |
|---|---|---|---|
| post_date | string | yes | Route date, yyyy-mm-dd. |
| plans | array | yes | — |
| driver_pay_locked_status | string | no | What to do with already locked driver pay: KEEP_LOCKED_AND_DISPATCH or UNLOCK_AND_DISPATCH. |
| confirm | boolean | yes | Must be true: the user approved this plan and wants it dispatched to the drivers now. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install CXT Software MCP by usefulapi or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.14.3 · scanned 6 Nov 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest71ad53b594b59cf0eb690fa6be343b84d2d8a3285a40bacab03f3c0a8ec7b6dc
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| cxt_track_shipments | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_search_shipments | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_list_recent_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_get_order | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_get_dispatch_order | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_get_planning_limits | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_validate_drivers | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_validate_driver_for_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_plan_orders | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_optimize_order_plan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_plan_routes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_optimize_route_plan | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| cxt_save_order_plan | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| cxt_save_route_plan | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest71ad53b594b59cf0
Scanned2026-11-06
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.14.3.
1.14.3
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish CXT Software MCP by usefulapi can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.